Browsing Τμήμα Μαθηματικών και Στατιστικής / Department of Mathematics and Statistics by Author "Polycarpou, Marios M."

Now showing items 1-9 of 9

    • Conference Object  

      Adaptive bounding techniques for stable neural control systems 

      Polycarpou, Marios M.; Ioannou, Petros A. (IEEE, 1995)
      This paper considers the design of stable adaptive neural controllers for uncertain nonlinear dynamical systems with unknown nonlinearities. The Lyapunov synthesis approach is used to develop state-feedback adaptive control ...
    • Conference Object  

      Convergence analysis for a class of neural networks 

      Polycarpou, Marios M.; Ioannou, Petros A. (Publ by IEEE, 1992)
      Summary form only given, as follows. The authors consider the convergence issue that arises in the application of backpropagation algorithms in a special class of neural network architectures, referred to as structured ...
    • Conference Object  

      Identification and control of aircraft dynamics using radial basis function networks 

      Ahmed-Zaid, F.; Ioannou, Petros A.; Polycarpou, Marios M.; Youssef, H. M. (Publ by IEEE, 1993)
      In this paper, we investigate one type of neural networks, namely the Radial Basis Functions (RBF) networks, and apply them to the identification and control problems of an aircraft system. The RBF network is used as an ...
    • Article  

      Learning and Convergence Analysis of Neural-Type Structured Networks 

      Polycarpou, Marios M.; Ioannou, Petros A. (1992)
      A special class of feedforward neural networks, referred to as structured networks, has recently been introduced as a method for solving matrix algebra problems in an inherently parallel formulation. In this paper we present ...
    • Conference Object  

      Learning techniques for structured networks 

      Polycarpou, Marios M.; Ioannou, Petros A. (Publ by American Automatic Control Council, 1991)
      A convergence analysis is presented for the training of structured networks. Since the learning techniques that are used in structured networks are the same as the ones used in training of neural networks, the issue of ...
    • Conference Object  

      Modelling, identification and stable adaptive control of continuous-time nonlinear dynamical systems using neural networks 

      Polycarpou, Marios M.; Ioannou, Petros A. (Publ by American Automatic Control Council, 1992)
      Several empirical studies have demonstrated the feasibility of employing neural networks as models of nonlinear dynamical systems. This paper develops the appropriate mathematical tools for synthesizing and analyzing stable ...
    • Article  

      On the Existence and Uniqueness of Solutions in Adaptive Control Systems 

      Polycarpou, Marios M.; Ioannou, Petros A. (1993)
      The issue of existence and uniqueness of solutions, which arises in the analysis of adaptive control systems, is investigated. We give sufficient conditions that guarantee existence and uniqueness in positive time of ...
    • Conference Object  

      Robust adaptive nonlinear control design 

      Polycarpou, Marios M.; Ioannou, Petros A. (Publ by IEEE, 1993)
      An adaptive control design procedure for a class of nonlinear systems with both parametric uncertainty and unknown nonlinearities is presented. The unknown nonlinearities lie within some 'bounding functions' which are ...
    • Article  

      A robust adaptive nonlinear control design 

      Polycarpou, Marios M.; Ioannou, Petros A. (1996)
      An adaptive control design procedure for a class of nonlinear systems with both parametric uncertainty and unknown nonlinearities is presented. The unknown nonlinearities lie within some 'bounding functions', which are ...